lkml.org 
[lkml]   [2020]   [Feb]   [24]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [LKP] Re: [perf/x86] 81ec3f3c4c: will-it-scale.per_process_ops -5.5% regression
On Mon, Feb 24, 2020 at 10:19:15AM +0800, Feng Tang wrote:
> >
> > > No, it's not the biggest, I tried another machine 'Xeon Phi(TM) CPU 7295',
> > > which has 72C/288T, and the regression is not seen. This is the part
> > > confusing me :)
> >
> > Hmm.
> >
> > Humor me - what happens if you turn off SMT on that Cascade Lake
> > system? Maybe it's about the thread ID bit in the L1? Although again,
> > I'd have expected things to get _worse_ if it's the two fields that
> > are now in the same cachline thanks to alignment.
>
> I'll try it and report back.

I added "nosmt=force" on the 2S 4 nodes 96C/192T machine, and tested
both 96 and 192 processes, and the regression still exists.

Also for Ying's suggestion about separate 'sigpending' to another cache
line than '__refcount', it can not heal the regression either.

Thanks,
Feng

\
 
 \ /
  Last update: 2020-02-24 14:20    [W:0.092 / U:0.072 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site